Case Study:
Business Research Project
Analysis of Company X Sales Trends
Company X is a well-known high technology company specializing in computer and Smartphone technology. It has experienced rapid growth in sales over the last decade with some slowing rate in this rate of growth in recent years (Statista, 2016). It generally announced new products or product updates every 18 to 24 months, but is wondering whether the rate of introducing updates to its models actually increases sales up to a certain rate of announcing updates and if too frequent, then the rate of growth of sales will be negatively impacted as people will increasingly evaluate whether new investments in the updated products is worthwhile. Thus, the two variables of interest are the annual percentage growth rate in sales as a dependent variable and the frequency of update announcements as the independent variable.
Company X needs to figure the optimal frequency at which it should announce updates to maximize its sales over the long term rather than focusing on short-term gains at the expense of potentially long-term growth. Therefore, the company should examine the length of time between product introductions/updates and the following quarter change in sales figures as well as changes in sales for 18 or 24 months following the product introduction/update. In other words, a statistical regression model might be specified as follows:
?Growth in Annual Sales?_t=B_0+ B_1 ?Time elapsed between new product introductions/updates?_(t-1)+ ?B_2 Time elapsed between new product introductions/updates?_(t-1)^2
The above equation will estimate the relationships,Β1 and Β2, between the time lapse between product introductions/updates during the last time period (t-1) with sales growth during the current period (t). The squared term allows to determine whether the relationship is indeed linear or whether there is a downturn at some point with increasing frequency.
It might be hypothesized that there is an optimal interval between product introductions/updates such that future sales growth is maximized. Thus, up to a point, more frequent product introductions/updates increase the growth in sales both in the short term and the long term and then beyond such an optimal frequency, long-term sales growth actually decreases even though short-term sales growth might be boosted by a new product introduction or update. It is hypothesized that this optimal frequency, if it does exist, would be in the range of 18 months to 2.5 years.
Thus, the team should probably analyze data going back to around 1998 when the company began to experience a resurgence after some thought that it would no longer exist. This would allow for a reasonably long time line and various lengths of product cycles or times between introductions to be examined in relationship to sales growth figures. As a result, any type of empirical results is likely to be more accurate the longer the time line examined. The team should not be necessarily looking for statistical significance but rather the magnitude and signs of the regression coefficients, Β1 and Β2, to ascertain the nature of the relationship between growth of sales and frequency of new product introductions/updates. If the sign on Β1 is positive and large and marginally statistically significant (p < 0.10) and the sign on Β2 is negative and marginally statistically significant (p< 0.10) then it might be assumed that there is an optimal frequency at which long-term sales growth might be maximized and this estimated equation could help determine this optimal frequency.
The business team would need to collect the data so that it could be entered into a database and statisticians would need to analyze the data in-house or perhaps it could be contracted out to a third-party. The team should then examine the results to determine whether they appear to make sense from a business perspective and whether the results can be used to develop business policy going forward. If so, then the company should attempt to limit new product introductions/updates in line with the empirical results obtained through an analysis of historical data. If implemented correctly, this may help to improve the bottom line of the company going forward into the distant future.
References:
Statista. (2016). Facts and statistics on Apple. Retrieved fromhttps://www.statista.com/topics/847/apple/